{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T23:54:23Z","timestamp":1768866863440,"version":"3.49.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T00:00:00Z","timestamp":1757376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Autom Softw Eng"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s10515-025-00552-2","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T02:21:09Z","timestamp":1757384469000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced neighborhood metric for spreadsheet fault prediction"],"prefix":"10.1007","volume":"33","author":[{"given":"Haitao","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiliang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"issue":"1","key":"552_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.jvlc.2006.06.001","volume":"18","author":"R Abraham","year":"2007","unstructured":"Abraham, R., Erwig, M.: Ucheck: A spreadsheet type checker for end users. J. Vis. Lang. Comput. 18(1), 71\u201395 (2007)","journal-title":"J. Vis. Lang. Comput."},{"issue":"1","key":"552_CR2","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/TSE.2008.73","volume":"35","author":"R Abraham","year":"2008","unstructured":"Abraham, R., Erwig, M.: Mutation operators for spreadsheets. IEEE Trans. Software Eng. 35(1), 94\u2013108 (2008)","journal-title":"IEEE Trans. Software Eng."},{"key":"552_CR3","doi-asserted-by":"crossref","unstructured":"Abreu, R., Cunha, J., Fernandes, J.P., et\u00a0al.: Faultysheet detective: When smells meet fault localization. In: 2014 IEEE International Conference on Software Maintenance and Evolution, pp. 625\u2013628. IEEE (2014a)","DOI":"10.1109\/ICSME.2014.111"},{"key":"552_CR4","doi-asserted-by":"crossref","unstructured":"Abreu, R., Cunha, J., Fernandes, J.P., et\u00a0al.: Smelling faults in spreadsheets. In: 2014 IEEE International Conference on Software Maintenance and Evolution, pp. 111\u2013120. IEEE (2014b)","DOI":"10.1109\/ICSME.2014.33"},{"key":"552_CR5","doi-asserted-by":"crossref","unstructured":"Barowy, D.W., Berger, E.D., Zorn, B.: Excelint: automatically finding spreadsheet formula errors. Proc. ACM Program. Lang. 2(OOPSLA):1\u201326 (2018)","DOI":"10.1145\/3276518"},{"key":"552_CR6","unstructured":"Bregar, A.: Complexity metrics for spreadsheet models (2008). arXiv:0802.3895"},{"issue":"1","key":"552_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"issue":"3","key":"552_CR8","first-page":"358","volume":"40","author":"L Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., et al.: Classification and regression trees (cart). Biom 40(3), 358 (1984)","journal-title":"Biom"},{"issue":"4","key":"552_CR9","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.jvlc.2009.04.002","volume":"20","author":"C Chambers","year":"2009","unstructured":"Chambers, C., Erwig, M.: Automatic detection of dimension errors in spreadsheets. J. Vis. Lang. Comput. 20(4), 269\u2013283 (2009)","journal-title":"J. Vis. Lang. Comput."},{"key":"552_CR10","unstructured":"Chen, X., Maniatis, P., Singh, R., et\u00a0al.: Spreadsheetcoder: Formula prediction from semi-structured context. In: International Conference on Machine Learning, pp. 1661\u20131672. PMLR (2021)"},{"issue":"12","key":"552_CR11","doi-asserted-by":"publisher","first-page":"4030","DOI":"10.14778\/3611540.3611613","volume":"16","author":"F Chen","year":"2023","unstructured":"Chen, F., Tang, D., Li, H., et al.: Visualizing spreadsheet formula graphs compactly. Proc. VLDB Endowment 16(12), 4030\u20134033 (2023)","journal-title":"Proc. VLDB Endowment"},{"key":"552_CR12","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"key":"552_CR13","doi-asserted-by":"crossref","unstructured":"Cunha, J., Fernandes, J.P., Martins, P., et\u00a0al.: Smellsheet detective: A tool for detecting bad smells in spreadsheets. In: 2012 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC), pp. 243\u2013244. IEEE (2012a)","DOI":"10.1109\/VLHCC.2012.6344535"},{"key":"552_CR14","doi-asserted-by":"crossref","unstructured":"Cunha, J., Fernandes, J.P., Ribeiro, H., et\u00a0al.: Towards a catalog of spreadsheet smells. In: International Conference on Computational Science and Its Applications, pp. 202\u2013216. Springer (2012b)","DOI":"10.1007\/978-3-642-31128-4_15"},{"key":"552_CR15","doi-asserted-by":"crossref","unstructured":"Dou, W., Cheung, S.C., Gao, C., et\u00a0al.: (2016a) Detecting table clones and smells in spreadsheets. In: Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering, pp. 787\u2013798","DOI":"10.1145\/2950290.2950359"},{"issue":"3","key":"552_CR16","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1109\/TSE.2016.2584059","volume":"43","author":"W Dou","year":"2016","unstructured":"Dou, W., Xu, C., Cheung, S.C., et al.: Cacheck: detecting and repairing cell arrays in spreadsheets. IEEE Trans. Software Eng. 43(3), 226\u2013251 (2016)","journal-title":"IEEE Trans. Software Eng."},{"key":"552_CR17","doi-asserted-by":"crossref","unstructured":"Fisher, M., Rothermel, G.: The euses spreadsheet corpus: a shared resource for supporting experimentation with spreadsheet dependability mechanisms. In: Proceedings of the first workshop on End-user software engineering, pp. 1\u20135 (2005)","DOI":"10.1145\/1083231.1083242"},{"key":"552_CR18","first-page":"102","volume-title":"2017 IEEE International Conference on Software Quality","author":"E Getzner","year":"2017","unstructured":"Getzner, E., Hofer, B., Wotawa, F.: Improving spectrum-based fault localization for spreadsheet debugging. In: 2017 IEEE International Conference on Software Quality, pp. 102\u2013113. Reliability and Security (QRS), IEEE (2017)"},{"key":"552_CR19","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT press (2016)"},{"key":"552_CR20","doi-asserted-by":"crossref","unstructured":"He, W., Dong, H., Gao, Y., et\u00a0al.: Hermes: Interactive spreadsheet formula prediction via hierarchical formulet expansion. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8356\u20138372. (2023)","DOI":"10.18653\/v1\/2023.acl-long.465"},{"key":"552_CR21","doi-asserted-by":"crossref","unstructured":"Hermans, F., Murphy-Hill, E.: Enron\u2019s spreadsheets and related emails: A dataset and analysis. In: 2015 IEEE\/ACM 37th IEEE International Conference on Software Engineering, pp. 7\u201316. IEEE (2015)","DOI":"10.1109\/ICSE.2015.129"},{"key":"552_CR22","unstructured":"Hermans, F., Pinzger, M., van Deursen, A.: Measuring spreadsheet formula understandability (2012a). arXiv:1209.3517"},{"key":"552_CR23","doi-asserted-by":"crossref","unstructured":"Hermans, F., Pinzger, M., Van\u00a0Deursen, A.: Detecting and visualizing inter-worksheet smells in spreadsheets. In: 2012 34th International Conference on Software Engineering (ICSE), pp. 441\u2013451. IEEE (2012b)","DOI":"10.1109\/ICSE.2012.6227171"},{"key":"552_CR24","doi-asserted-by":"crossref","unstructured":"Hermans, F., Pinzger, M., Van\u00a0Deursen, A.: Detecting code smells in spreadsheet formulas. In: 2012 28th IEEE International Conference on Software Maintenance (ICSM), pp. 409\u2013418. IEEE (2012c)","DOI":"10.1109\/ICSM.2012.6405300"},{"key":"552_CR25","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/s10664-013-9296-2","volume":"20","author":"F Hermans","year":"2015","unstructured":"Hermans, F., Pinzger, M., van Deursen, A.: Detecting and refactoring code smells in spreadsheet formulas. Empir. Softw. Eng. 20, 549\u2013575 (2015)","journal-title":"Empir. Softw. Eng."},{"key":"552_CR26","unstructured":"Hodnigg, K., Mittermeir, R.T.: Metrics-based spreadsheet visualization: Support for focused maintenance (2008). arXiv:0809.3009"},{"key":"552_CR27","unstructured":"Hofer, B., Riboira, A., Wotawa, F., et\u00a0al.: On the empirical evaluation of fault localization techniques for spreadsheets. In: Fundamental Approaches to Software Engineering: 16th International Conference, FASE 2013, Held as Part of the European Joint Conferences on Theory and Practice of Software, ETAPS 2013, Rome, Italy, March 16-24, 2013, pp. 68\u201382. Proceedings 16, Springer (2013)"},{"key":"552_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An Introduction to Statistical Learning","author":"G James","year":"2013","unstructured":"James, G., Witten, D., Hastie, T., et al.: An Introduction to Statistical Learning, vol. 112. Springer (2013)"},{"key":"552_CR29","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.jss.2014.03.058","volume":"94","author":"D Jannach","year":"2014","unstructured":"Jannach, D., Schmitz, T., Hofer, B., et al.: Avoiding, finding and fixing spreadsheet errors-a survey of automated approaches for spreadsheet qa. J. Syst. Softw. 94, 129\u2013150 (2014)","journal-title":"J. Syst. Softw."},{"issue":"10","key":"552_CR30","doi-asserted-by":"publisher","first-page":"2195","DOI":"10.1109\/TSE.2019.2944604","volume":"47","author":"P Koch","year":"2019","unstructured":"Koch, P., Schekotihin, K., Jannach, D., et al.: Metric-based fault prediction for spreadsheets. IEEE Trans. Software Eng. 47(10), 2195\u20132207 (2019)","journal-title":"IEEE Trans. Software Eng."},{"key":"552_CR31","doi-asserted-by":"crossref","unstructured":"Kudebayeva, A., Harte, C., Bryan-Kinns, N., et\u00a0al.: To abstract or not to abstract? a comparative study evaluating the user experience of spreadsheet programming with sheet-defined functional abstractions, pp. 1\u201317. International Journal of Human\u2013Computer Interaction (2024)","DOI":"10.1080\/10447318.2024.2361209"},{"issue":"474","key":"552_CR32","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1198\/016214505000001230","volume":"101","author":"Y Lin","year":"2006","unstructured":"Lin, Y., Jeon, Y.: Random forests and adaptive nearest neighbors. J. Am. Stat. Assoc. 101(474), 578\u2013590 (2006)","journal-title":"J. Am. Stat. Assoc."},{"key":"552_CR33","unstructured":"Reschenhofer, T., Waltl, B., Shumaiev, K., et\u00a0al.: A conceptual model for measuring the complexity of spreadsheets (2017). arXiv:1704.01147"},{"key":"552_CR34","unstructured":"Schapire, R.E., et\u00a0al.: A brief introduction to boosting. In: Ijcai, Citeseer, pp. 1401\u20131406. (1999)"},{"key":"552_CR35","doi-asserted-by":"crossref","unstructured":"Schmitz, T., Jannach, D.: Finding errors in the enron spreadsheet corpus. In: 2016 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC), pp. 157\u2013161. IEEE (2016)","DOI":"10.1109\/VLHCC.2016.7739679"},{"key":"552_CR36","unstructured":"Singh, R., Livshits, B., Zorn, B.: Melford: Using neural networks to find spreadsheet errors. Microsoft Research, Microsoft Tech Report Number MSR-TR-2017-5, Tech Rep (2017)"},{"key":"552_CR37","first-page":"423","volume-title":"2018 IEEE 25th International Conference on Software Analysis","author":"L Xu","year":"2018","unstructured":"Xu, L., Wang, S., Dou, W., et al.: Detecting faulty empty cells in spreadsheets. In: 2018 IEEE 25th International Conference on Software Analysis, pp. 423\u2013433. Evolution and Reengineering (SANER), IEEE (2018)"},{"key":"552_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lv, X., Dong, H., et\u00a0al.: Semantic table structure identification in spreadsheets. In: Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 283\u2013295. (2021)","DOI":"10.1145\/3460319.3464812"},{"key":"552_CR39","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.jss.2016.03.061","volume":"126","author":"R Zhang","year":"2017","unstructured":"Zhang, R., Xu, C., Cheung, S.C., et al.: How effectively can spreadsheet anomalies be detected: An empirical study. J. Syst. Softw. 126, 87\u2013100 (2017)","journal-title":"J. Syst. Softw."}],"container-title":["Automated Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00552-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10515-025-00552-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10515-025-00552-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T11:14:58Z","timestamp":1768821298000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10515-025-00552-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,9]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["552"],"URL":"https:\/\/doi.org\/10.1007\/s10515-025-00552-2","relation":{},"ISSN":["0928-8910","1573-7535"],"issn-type":[{"value":"0928-8910","type":"print"},{"value":"1573-7535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,9]]},"assertion":[{"value":"11 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2025","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Minor corrections has been updated throughout the article and funding information is updated in the Acknowledgment section.","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2"}}